Cascaded Reinforcement Learning Agents for Large Action Spaces in Autonomous Penetration Testing
Open Access
- 7 November 2022
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 12 (21) , 11265
Abstract
Organised attacks on a computer system to test existing defences, i.e., penetration testing, have been used extensively to evaluate network security. However, penetration testing is a time-consuming process. Additionally, establishing a strategy that resembles a real cyber-attack typically requires in-depth knowledge of the cybersecurity domain. This paper presents a novel architecture, named deep cascaded reinforcement learning agents, or CRLA, that addresses large discrete action spaces in an autonomous penetration testing simulator, where the number of actions exponentially increases with the complexity of the designed cybersecurity network. Employing an algebraic action decomposition strategy, CRLA is shown to find the optimal attack policy in scenarios with large action spaces faster and more stably than a conventional deep Q-learning agent, which is commonly used as a method for applying artificial intelligence to autonomous penetration testing.Keywords
Funding Information
- Defence Science and Technology Organisation (MyIP 10699)
This publication has 12 references indexed in Scilit:
- Automated Penetration Testing Using Deep Reinforcement Learning2020
- Reinforcement Learning for Efficient Network Penetration TestingInformation, 2019
- Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space2019
- Neural-Linear Architectures for Sequential Decision Making2019
- Action Branching Architectures for Deep Reinforcement LearningProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Rainbow: Combining Improvements in Deep Reinforcement LearningProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Reinforcement Learning with Parameterized ActionsProceedings of the AAAI Conference on Artificial Intelligence, 2016
- Human-level control through deep reinforcement learningNature, 2015
- Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents1993
- Q-learningMachine Learning, 1992